© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12096
    Prev
    Next
    INDEX
    Explanations

    mentions of a smaller amount/number of something

    oai_token-act-pair · gemini-2.0-flash

    fewer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.78
     We
    -0.75
     @
    -0.73
     Mc
    -0.69
     Re
    -0.69
     My
    -0.68
     +
    -0.65
     __
    -0.65
     You
    -0.63
     Back
    -0.63
    POSITIVE LOGITS
     ་་
    1.35
    Personensuche
    1.32
    <bos>
    1.21
    GEBURTSDATUM
    1.20
     bezeichneter
    1.15
     Мексичка
    1.13
    expandindo
    1.08
     ―――――
    1.08
    />";
    1.03
     дописавши
    1.02
    Activations Density 0.693%

    No Known Activations